Search Results for author:
Found 5 papers, 0 papers with code
On an Interpretation of ResNets via Solution Constructions
This paper first constructs a typical solution of ResNets for multi-category classifications by the principle of gate-network controls and deep-layer classifications, from which a general interpretation of the ResNet architecture is given and the performance mechanism is explained.
Universal Solutions of Feedforward ReLU Networks for Interpolations
To deep-layer networks, we present a general result called sparse-matrix principle, which could describe some basic behavior of deep layers and explain the phenomenon of the sparse-activation mode that appears in engineering applications associated with brain science; an advantage of deep layers compared to shallower ones is manifested in this principle.
On a Mechanism Framework of Autoencoders
To the encoder part, under the main use of dimensionality reduction, we investigate its two fundamental properties: bijective maps and data disentangling.
Theoretical Exploration of Solutions of Feedforward ReLU Networks
This paper aims to interpret the mechanism of feedforward ReLU networks by exploring their solutions for piecewise linear functions, through the deduction from basic rules.
Interpretations of Deep Learning by Forests and Haar Wavelets
Finally, generalize some of the conclusions of ReLU deep learning to the case of sigmoid-unit deep learning.
